Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mooshare.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urllib_parse
   7 from ..utils import (
   8     ExtractorError,
   9     sanitized_Request,
  10 )
  11
  12
  13 class MooshareIE(InfoExtractor):
  14     IE_NAME = 'mooshare'
  15     IE_DESC = 'Mooshare.biz'
  16     _VALID_URL = r'http://(?:www\.)?mooshare\.biz/(?P<id>[\da-z]{12})'
  17
  18     _TESTS = [
  19         {
  20             'url': 'http://mooshare.biz/8dqtk4bjbp8g',
  21             'md5': '4e14f9562928aecd2e42c6f341c8feba',
  22             'info_dict': {
  23                 'id': '8dqtk4bjbp8g',
  24                 'ext': 'mp4',
  25                 'title': 'Comedy Football 2011 - (part 1-2)',
  26                 'duration': 893,
  27             },
  28         },
  29         {
  30             'url': 'http://mooshare.biz/aipjtoc4g95j',
  31             'info_dict': {
  32                 'id': 'aipjtoc4g95j',
  33                 'ext': 'mp4',
  34                 'title': 'Orange Caramel  Dashing Through the Snow',
  35                 'duration': 212,
  36             },
  37             'params': {
  38                 # rtmp download
  39                 'skip_download': True,
  40             }
  41         }
  42     ]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46         page = self._download_webpage(url, video_id, 'Downloading page')
  47
  48         if re.search(r'>Video Not Found or Deleted<', page) is not None:
  49             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  50
  51         hash_key = self._html_search_regex(r'<input type="hidden" name="hash" value="([^"]+)">', page, 'hash')
  52         title = self._html_search_regex(r'(?m)<div class="blockTitle">\s*<h2>Watch ([^<]+)</h2>', page, 'title')
  53
  54         download_form = {
  55             'op': 'download1',
  56             'id': video_id,
  57             'hash': hash_key,
  58         }
  59
  60         request = sanitized_Request(
  61             'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form))
  62         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  63
  64         self._sleep(5, video_id)
  65
  66         video_page = self._download_webpage(request, video_id, 'Downloading video page')
  67
  68         thumbnail = self._html_search_regex(r'image:\s*"([^"]+)",', video_page, 'thumbnail', fatal=False)
  69         duration_str = self._html_search_regex(r'duration:\s*"(\d+)",', video_page, 'duration', fatal=False)
  70         duration = int(duration_str) if duration_str is not None else None
  71
  72         formats = []
  73
  74         # SD video
  75         mobj = re.search(r'(?m)file:\s*"(?P<url>[^"]+)",\s*provider:', video_page)
  76         if mobj is not None:
  77             formats.append({
  78                 'url': mobj.group('url'),
  79                 'format_id': 'sd',
  80                 'format': 'SD',
  81             })
  82
  83         # HD video
  84         mobj = re.search(r'\'hd-2\': { file: \'(?P<url>[^\']+)\' },', video_page)
  85         if mobj is not None:
  86             formats.append({
  87                 'url': mobj.group('url'),
  88                 'format_id': 'hd',
  89                 'format': 'HD',
  90             })
  91
  92         # rtmp video
  93         mobj = re.search(r'(?m)file: "(?P<playpath>[^"]+)",\s*streamer: "(?P<rtmpurl>rtmp://[^"]+)",', video_page)
  94         if mobj is not None:
  95             formats.append({
  96                 'url': mobj.group('rtmpurl'),
  97                 'play_path': mobj.group('playpath'),
  98                 'rtmp_live': False,
  99                 'ext': 'mp4',
 100                 'format_id': 'rtmp',
 101                 'format': 'HD',
 102             })
 103
 104         return {
 105             'id': video_id,
 106             'title': title,
 107             'thumbnail': thumbnail,
 108             'duration': duration,
 109             'formats': formats,
 110         }